Vehicle driving test method and device, intelligent cabin system, equipment and medium

Abstract

The invention discloses a vehicle driving test method and device, an intelligent cabin system, equipment and a medium. The method comprises the steps that area information and environment parameters of a test area are acquired; generating a sensor configuration strategy of the test vehicle based on the area information, and performing sensor configuration on the test vehicle based on the sensor configuration strategy to obtain a sensor unit corresponding to the test vehicle; performing interference coefficient prediction on the sensor unit based on the environmental parameters to obtain an interference coefficient of the environmental factors on the sensor; virtual-real bidirectional mapping is carried out based on the interference coefficient and the area information, and a driving test digital twin system corresponding to the test area is constructed; and controlling the test vehicle to perform virtual driving test in the driving test digital twin system to obtain a test result. The problems that the authenticity of the virtual test environment is poor and the accuracy of vehicle testing is low due to the fact that invisible influence factors are not considered in the existing virtual test environment are solved.

Description

Background Art

[0002] With the continuous iteration of automotive technologies, the industry's requirements for vehicle performance have been rising steadily. In the process of vehicle R & D, vehicle driving tests are a crucial link. Through rigorous and comprehensive driving tests, vehicle performance can be accurately evaluated to ensure that its various indicators meet or even exceed the expected standards, laying a solid foundation for the birth of high-quality vehicles.

[0003] To improve safety during the testing process, virtual driving tests on vehicles are often carried out through data interaction in the existing technology. However, generally only the basic road information visible in the real environment is available in the virtual test environment, and invisible influencing factors are not considered, resulting in a poor authenticity of the virtual test environment and a low accuracy of vehicle testing. Summary of the Invention

[0004] To overcome the problem that generally only the basic road information visible in the real environment is available in the existing virtual test environment, and invisible influencing factors are not considered, resulting in a poor authenticity of the virtual test environment and a low accuracy of vehicle testing, this application provides a vehicle driving test method, device, intelligent cockpit system, equipment and medium.

[0005] In a first aspect, to solve the above technical problem, this application provides a vehicle driving test method, including:

[0006] Obtain the area information and environmental parameters of the test area;

[0007] Generate a sensor configuration strategy for the test vehicle based on the area information, and configure the sensors of the test vehicle based on the sensor configuration strategy to obtain a sensor unit corresponding to the test vehicle, where the sensor unit includes one or more sensors;

[0008] Predict the interference coefficient of the sensor unit based on the environmental parameters to obtain the interference coefficient of the environmental factors on the sensors;

[0009] Perform virtual-real bidirectional mapping based on the interference coefficient and the area information to construct a driving test digital twin system corresponding to the test area, where the driving test digital twin system is used to map the physical system corresponding to the test area;

[0010] Control the test vehicle to perform virtual driving tests in the driving test digital twin system to obtain test results.

[0011] In a second aspect, this application also provides a vehicle driving test device, including:

[0012] An acquisition module, configured to acquire the area information and environmental parameters of the test area;

[0013] A strategy generation module, configured to generate a sensor configuration strategy for a test vehicle based on regional information, and configure sensors on the test vehicle based on the sensor configuration strategy to obtain a sensor unit corresponding to the test vehicle, where the sensor unit includes one or more sensors;

[0014] A prediction module, configured to predict an interference coefficient of the sensor unit based on environmental parameters to obtain an interference coefficient of the environment on the sensor;

[0015] A construction module, configured to perform virtual-real bidirectional mapping based on the interference coefficient and regional information to construct a digital twin system for driving tests corresponding to a test area, where the digital twin system for driving tests is used to map the physical system corresponding to the test area;

[0016] A driving test module, configured to control the test vehicle to perform virtual driving tests in the digital twin system for driving tests to obtain test results.

[0017] In a third aspect, the present application further provides an intelligent cockpit system, which applies the vehicle driving test method described above. The intelligent cockpit system includes:

[0018] A data acquisition device, configured to acquire regional information and environmental parameters of a test area;

[0019] A sensor unit, configured on the test vehicle according to a sensor configuration strategy generated based on regional information;

[0020] An intelligent cockpit, configured to perform virtual driving tests in the constructed digital twin system for driving tests instead of the test vehicle to obtain test results;

[0021] The data acquisition device, the sensor unit, and the intelligent cockpit are communicatively connected to each other.

[0022] In a fourth aspect, the present application further provides a computing device, including a memory, a processor, and a program stored on the memory and running on the processor. When the processor executes the program, it implements the steps of the vehicle driving test method described above.

[0023] In a fifth aspect, the present application further provides a computer-readable storage medium, in which instructions are stored. When the instructions run on a terminal device, the terminal device is caused to execute the steps of a vehicle driving test method.

[0024] The beneficial effects of the present application are as follows: First, a sensor configuration strategy for the test vehicle is generated based on the regional information of the test area, and the test vehicle is configured with sensors based on this sensor configuration strategy, so that the configured sensors can match the test area for vehicle testing, reducing the participation of useless sensors in the test and saving test costs. Then, the interference coefficient of the sensor unit is predicted based on the environmental parameters of the test area to obtain the interference coefficient of the environmental factors on the sensors, and a virtual-real bidirectional mapping is performed based on the interference coefficient and the regional information to construct a digital twin system for driving tests corresponding to the test area. The digital twin system for driving tests is a physical system corresponding to the mapped test area, and the test vehicle is controlled to perform virtual driving tests in the digital twin system for driving tests to obtain test results. In this way, both the invisible environmental parameters and the visible regional information of the test area can be added to the corresponding digital twin system to improve the authenticity of the constructed digital twin system for driving tests, making the data collected by the sensors configured on the test vehicle during the virtual driving test highly matched with the real information of the test area, improving the accuracy of the test results obtained from the test, and thus being able to improve the accuracy of vehicle testing. Description of the Drawings

[0025] Figure 1 It is a schematic flowchart of a vehicle driving test method shown in an exemplary embodiment of the present application;

[0026] Figure 2 It is a schematic structural diagram of a vehicle driving test device shown in an exemplary embodiment of the present application. Detailed Embodiments

[0027] The following embodiments are further explanations and supplements to the present application and do not constitute any limitation to the present application.

[0028] In the prior art, real road traffic scene information of autonomous vehicles is collected through road tests, and digital twin technology is used to generate virtual simulation scenarios. VR display devices are equipped in the vehicle, enabling drivers to enter the digital virtual scenario through virtual simulation software running on in-vehicle industrial computers for testing. However, the influence of natural environments such as rainy days, foggy days, and sunlight irradiation angles on sensors is not considered, resulting in a certain deviation from actual road tests, poor authenticity of the generated virtual simulation scenarios, and low accuracy of vehicle testing.

[0029] To solve the above problems, embodiments of the present application provide a vehicle driving test method, device, intelligent cockpit system, device, and medium, which will be described in detail below.

[0030] In this application, all actions for obtaining signals, information, or data are carried out on the basis of strictly following the relevant data protection regulations and policies of the country where the device is located and with the authorization of the owner of the corresponding device.

[0031] The owner refers to an individual or entity that owns or controls the relevant device (which may be a device, system, or other tool that can collect data).

[0032] In the field of intelligent connected vehicles, "owners" mainly include:

[0033] (1) Automobile manufacturers: As developers of vehicle hardware and systems, they control the underlying vehicle hardware and software platforms and have management and control rights over the data generated during vehicle operation, such as driving and fault data.

[0034] (2) Component suppliers: Provide key components for the vehicle and have certain ownership of the data collected and processed by the components for product optimization and after-sales service, such as data generated by sensors and chips.

[0035] (3) Vehicle owners or users: The actual users of the vehicle, who have the right to decide on the usage method and scope of vehicle data, such as whether to share data on driving trajectories and driving habits, and have the need and right to protect their own relevant data privacy.

[0036] (4) Service providers: Provide services such as software and data analysis, and have the right to use and manage the data obtained and processed within the framework of the agreement, but the ownership usually belongs to other entities.

[0037] A vehicle driving test method provided by an embodiment of this application can be specifically executed by a server. It should be noted that the server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms, and there is no limitation here.

[0038] Please refer to Figure 1 , Figure 1 which shows a vehicle driving test method shown in an exemplary embodiment of this application. As Figure 1 shown, this application provides a vehicle driving test method, including:

[0039] Step S11, obtaining the area information and environmental parameters of the test area;

[0040] Step S12: Generate a sensor configuration strategy for the test vehicle based on the area information, and configure the sensors of the test vehicle based on the sensor configuration strategy to obtain a sensor unit corresponding to the test vehicle, where the sensor unit includes one or more sensors;

[0041] Step S13: Predict the interference coefficient of the sensor unit based on the environmental parameters to obtain the interference coefficient of the environment on the sensor;

[0042] Step S14: Perform two-way virtual-real mapping based on the interference coefficient and the area information to construct a driving test digital twin system corresponding to the test area, where the driving test digital twin system is used to map the physical system corresponding to the test area;

[0043] Step S15: Control the test vehicle to perform a virtual driving test in the driving test digital twin system to obtain a test result.

[0044] In the vehicle driving test method provided in this embodiment of the present application, first, a sensor configuration strategy for the test vehicle is generated based on the area information of the test area, and the sensors of the test vehicle are configured based on the sensor configuration strategy, so that the configured sensors can match the test area for vehicle testing, reduce the participation of useless sensors in the test, and save the test cost. Then, the interference coefficient of the sensor unit is predicted based on the environmental parameters of the test area to obtain the interference coefficient of the environment on the sensor, and two-way virtual-real mapping is performed based on the interference coefficient and the area information to construct a driving test digital twin system corresponding to the test area. The driving test digital twin system maps the physical system corresponding to the test area, and controls the test vehicle to perform a virtual driving test in the driving test digital twin system to obtain a test result. In this way, the invisible environmental parameters and visible area information of the test area can be added to the corresponding digital twin system to improve the authenticity of the constructed driving test digital twin system, so that the data collected by the sensors configured on the test vehicle during the virtual driving test matches the real information of the test area with a high degree, improving the accuracy of the test result obtained by the test, and thus improving the accuracy of the vehicle test.

[0045] In an exemplary embodiment provided by the present application, first, through an efficient data transmission and processing algorithm, the area information of the test area is subjected to feature extraction and feature fusion to form a comprehensive perception of the traffic environment, so that the area information is real-time mapped into the simulation system. In the simulation system, a corresponding road model, traffic participant model, and traffic facility model are constructed to form a real-time initial digital twin system of the test area, and the digital twin system is displayed with a high-fidelity graphical interface using three-dimensional modeling and visualization technology, thereby constructing an initial digital twin system highly similar to the real area information of the test area.

[0046] Then, map the interference coefficient of the test area to the initial digital twin system to introduce the environmental parameters formed by the weather and sunlight irradiation in the test area into the initial digital twin system, and obtain a driving test digital twin system with environmental parameters that are more suitable for the test area and invisible. Among them, the weather includes rainy days, sunny days, cloudy days, foggy days, snowy days, etc., the sunlight irradiation includes direct sunlight, oblique sunlight and other different angles of sunlight irradiation, and the environmental parameters formed by the weather and sunlight irradiation include temperature parameters, humidity parameters and light intensity parameters.

[0047] Optionally, predict the interference coefficient of the sensor unit based on the environmental parameters to obtain the interference coefficient of the environmental factors on the sensor, including:

[0048] Input the environmental parameters into a preset interference coefficient prediction model to obtain the interference coefficient corresponding to the sensor output by the interference coefficient prediction model;

[0049] Among them, the environmental parameters include temperature parameters, humidity parameters and light intensity parameters;

[0050] The interference coefficient corresponding to the sensor includes a temperature interference coefficient, a humidity interference coefficient and a light intensity interference coefficient.

[0051] In this embodiment provided by the present application, through the pre-constructed interference coefficient prediction model that meets the accuracy requirements for each sensor, when it is necessary to obtain the interference coefficient of a certain sensor under an environmental parameter in the test area, the corresponding interference coefficient can be directly obtained by using the interference coefficient prediction model corresponding to the sensor to process the environmental parameter. In this way, using the pre-constructed model can conveniently and quickly obtain the interference coefficient corresponding to the environmental parameter, without the need for complex calculations each time, improving the acquisition efficiency of the interference coefficient of the sensor. At the same time, the interference coefficient is a data form that can be recognized by the digital twin system. By converting the environmental parameters of the test area into interference coefficients, it is convenient to add the environmental parameters to the digital twin system corresponding to the test area in the form of interference coefficient data later, so as to improve the authenticity of the obtained driving test digital twin system, thereby improving the accuracy of vehicle testing.

[0052] Optionally, the construction method of the interference coefficient prediction model includes:

[0053] Collect environmental monitoring data. The environmental monitoring data includes data obtained by monitoring environmental physical quantities under different environmental conditions. The environmental physical quantities include temperature, humidity and light intensity;

[0054] Obtain the output signal of each sensor in the test area under different environmental conditions;

[0055] Input the output signal and the environmental monitoring data into a preset initial model for training to obtain the model output;

[0056] Optimize and adjust the initial model based on the model output to obtain an interference coefficient prediction model.

[0057] In this embodiment provided by the present application, the output signals of the sensor under different environmental conditions and the environmental monitoring data under different environmental conditions are input into a preset initial model for training to optimize and adjust the initial model, so that the trained interference coefficient prediction model of the sensor can directly process environmental parameters to obtain an interference coefficient with the accuracy of the sensor meeting the requirements under the environmental parameters, improving the determination efficiency and accuracy of the interference coefficient, and thus being able to provide the authenticity of the driving test digital twin system constructed based on the interference coefficient and improving the accuracy of vehicle testing.

[0058] In an exemplary embodiment provided by the present application, when the sensor is under different environmental conditions, the degree of interference is different. For example, when the sensor is a lidar, in rainy weather, rainwater may scatter and absorb the laser beam of the lidar, thus affecting its ranging accuracy. Another example is that when the sensor is a camera, under strong light illumination, the camera may experience overexposure, resulting in a decline in image quality.

[0059] In order to standardize the interference of different environmental conditions on the sensor into a data form that can be recognized by a machine, the output signals under different environmental conditions and the environmental monitoring data under different environmental conditions are used to train a preset initial model to obtain an interference coefficient prediction model that can standardize the interference of different environmental conditions on the sensor into an interference coefficient. The preset initial model is a prediction model of the interference coefficient of environmental factors established using algorithms such as deep learning, that is, the initial model includes an environmental mathematical model established based on the output signals of the sensor under different environmental conditions and the environmental conditions. This environmental mathematical model is expressed as V = V0 + k t (T - T0) + k h (H - H0) + k l (L - L0), where V represents the current output signal of the sensor, V0 represents the output signal of the sensor under reference conditions, k t 、k h 、k l respectively represent the interference coefficients of the temperature parameter, humidity parameter, and light intensity parameter, T, H, and L respectively represent the current temperature parameter, humidity parameter, and light intensity parameter, and T0, H0, and L0 respectively represent the temperature parameter, humidity parameter, and light intensity parameter under reference conditions. The initial model of the sensor is trained and verified through the environmental data set formed by the output signals of the sensor under different environmental conditions, and the initial model of the sensor is continuously improved to obtain a corresponding interference coefficient prediction model that meets the accuracy requirements.

[0060] Optionally, the test vehicle is controlled to perform a virtual driving test in the driving test digital twin system to obtain test results, including:

[0061] Determining a region type of the test region based on the region information;

[0062] Determine the corresponding test requirements based on the area information and area type;

[0063] Determine the driving operation strategy of the test vehicle based on the test requirements;

[0064] Control the test vehicle to perform virtual driving tests in the driving test digital twin system according to the driving operation strategy to obtain test data;

[0065] A test result is generated based on the test data.

[0066] In the embodiment provided by the present application, according to the regional information of the test area, the basic structure and use scenario of the test area can be understood, so as to directly obtain the regional type to which the test area belongs. And through the regional type, it is possible to understand the test type that the test area can perform, and through the test type and regional information, it is possible to understand the test operation specification that the test area needs to perform, so as to form a corresponding test requirement based on the test operation specification of the test area. Then, based on the test requirements, the driving operation strategy that needs to be executed when the test operation specification is implemented can be planned, so as to control the test vehicle to perform a virtual driving test according to the driving operation strategy in the driving test digital twin system, and obtain the test data corresponding to the test requirements. In this way, the driving operation strategy is set according to the test requirements of the test area, and automatic testing is performed in the driving test virtual twin system based on the driving operation strategy. The test is highly targeted based on the test requirements, so as to improve the efficiency and accuracy of vehicle testing.

[0067] In another exemplary embodiment provided by the present application, the area type may be a parking lot, urban road, highway, rural road, park, etc.; the test requirements may be automatic reverse parking test requirements, automatic parallel parking test requirements, automatic obstacle avoidance test requirements, traffic light passing test requirements, safety test requirements, performance test requirements, reliability test requirements, comfort test requirements, regulatory compliance test requirements, etc. The safety test requirements include collision test requirements, braking test requirements, rollover test requirements, etc. The performance test requirements include power performance test requirements, handling performance test requirements, NVH (Noise, Vibration, Harshness) test requirements, etc. The reliability test requirements include durability test requirements, environmental adaptability test requirements, electronic system test requirements, etc. The comfort test requirements include seat comfort test requirements, air conditioning system test requirements, etc. The regulatory compliance test requirements include emission test requirements, lighting test requirements, etc. In addition, the test requirements are set according to the functional requirements and test standards of different levels (L2-L5) of autonomous driving.

[0068] Optionally, the test area is configured with a data acquisition device; the area information of the test area is obtained, including:

[0069] The initial area information of the test area is collected by using the data acquisition device, and the initial area information includes initial road information, initial traffic participant information, and initial traffic facility information;

[0070] The initial area information is subjected to spatio-temporal synchronization processing and spatial alignment processing to obtain the area information of the test area.

[0071] In this embodiment provided by the present application, the initial area information of the test area is collected by using the data acquisition device, and the initial area information is subjected to data cleaning processing and data conversion processing, so that the initial area information is subjected to spatio-temporal synchronization processing and spatial alignment, so that the obtained area information maintains data consistency and accuracy, and reduces the interference of the interference data generated by data inconsistency to the construction of the driving test digital twin system, thereby improving the accuracy and efficiency of the constructed driving test digital twin system, and further improving the accuracy of subsequent vehicle tests. Among them, the initial road information includes the shape, slope, curvature, number and width of lanes of the road, the initial traffic participant information includes the type, speed, driving trajectory of the vehicle, the position and movement direction of pedestrians, etc., and the initial traffic facility information includes the status of traffic lights, the position and content of traffic signs, etc.

[0072] In another exemplary embodiment provided by the present application, the data acquisition device includes a roadside computing unit (RCU), a roadside unit (RSU), a camera, a radar, etc.

[0073] Optionally, generate a sensor configuration strategy for the test vehicle based on the area information, including:

[0074] Determine the area type of the test area based on the area information;

[0075] Search for the alternative sensor configuration strategy corresponding to the area type from the preset configuration strategy library, and use the alternative sensor configuration strategy as the sensor configuration strategy of the test vehicle.

[0076] In this embodiment provided by the present application, according to the area information of the test area, the basic structure and usage scenario of the test area can be understood, so as to directly obtain the area type to which the test area belongs. And search for the sensor configuration strategy of the test vehicle corresponding to the area type from the preset configuration strategy library. In this way, it is not necessary for engineers to design a matching sensor configuration strategy on site every time a vehicle test is carried out, but directly search from the preset configuration strategy library, which improves the selection efficiency and configuration efficiency of the sensors, and thus can improve the test efficiency of the vehicle.

[0077] In an exemplary embodiment provided by the present application, the sensors in the sensor unit configured based on the sensor configuration strategy can be one or more of lidar, camera, millimeter wave radar, and ultrasonic radar. Among them, the high-precision lidar can be an in-vehicle high-precision FWCW lidar for accurately measuring the distance and position of surrounding environmental objects of the vehicle; the camera includes but is not limited to a front view camera, a surround view camera, a rear view camera, and a side view camera for capturing visual image information around the vehicle; the millimeter wave radar is used to detect the relative speed and distance between the vehicle and surrounding objects; the ultrasonic radar is used to detect the distance of obstacles around the vehicle.

[0078] Through a large number of preliminary tests and data analysis, according to the scenarios and test requirements of different test areas, determine the sensor configuration strategy for the optimal configuration position and quantity of the sensors of the test vehicle. For example, when it is determined that the area type of the test area is a highway based on the area information, since the focus is on the front and side during autonomous driving on the highway, the alternative sensor configuration strategy corresponding to the area type is searched from the preset configuration strategy library, which is to configure a front view camera above the windshield of the vehicle, a side view camera on each of the two side mirrors, and deploy a lidar on the top of the vehicle. Using this alternative sensor configuration strategy as the sensor configuration strategy of the test vehicle can achieve full-range perception around the body of the test vehicle. Even in bad weather (such as heavy rain, heavy snow, foggy weather), the lidar can provide high-precision target detection to ensure the safety of vehicle autonomous driving.

[0079] In an exemplary embodiment provided by the present application, before the test vehicle conducts a test, the test area that needs to be tested and analyzed this time, as well as the data information (area information and environmental parameters) of the test area that needs to be collected, are preset in advance. Then, a standard comparison library for the test is selected for confirmation and the test is started. After the test is completed, one-key analysis is initiated. The system compares the test data obtained from the test with the data in the standard comparison library to obtain a test result, automatically outputs the test result as a test report for preview, and modifies the incorrect results in the test report while retaining the modification records to ensure the accuracy and traceability of the test result.

[0080] During the process of the test vehicle conducting virtual driving tests in the driving test digital twin system, testers can, through VR glasses, observe in real time information such as road conditions, behaviors of traffic participants, and driving states of the vehicle in the simulated driving test digital twin system. At the same time, combined with the actual operation experience in the laboratory, the performance of the autonomous driving system can be comprehensively evaluated. This test method in the laboratory environment can not only effectively reduce test costs and risks, but also improve test efficiency and accuracy, providing strong support for the research and development and optimization of autonomous driving technology.

[0081] A vehicle driving test method of the present application, when constructing a driving test digital twin system for the test area, introduces the environmental parameters of the test area, realizes a highly restored real traffic scene of the test area, provides a more comprehensive and real test environment for autonomous driving tests, and greatly improves the accuracy and reliability of test results. At the same time, through the precise modeling and simulation of the environmental parameters of the test area, the impacts of various complex weather and sunlight conditions on sensors and autonomous driving systems are considered, further enhancing the comprehensiveness, practicality, and authenticity of the test. Moreover, the test method based on VR technology provides an immersive test experience for testers, improving test efficiency and the controllability of the test process.

[0082] Please refer to Figure 2 , Figure 2 which shows a vehicle driving test device shown in an exemplary embodiment of the present application. As Figure 2 shown, the present application provides a vehicle driving test device 200, including:

[0083] An acquisition module 201, configured to acquire area information and environmental parameters of a test area;

[0084] A strategy generation module 202, configured to generate a sensor configuration strategy for a test vehicle based on the area information, and perform sensor configuration on the test vehicle based on the sensor configuration strategy to obtain a sensor unit corresponding to the test vehicle, where the sensor unit includes one or more sensors;

[0085] A prediction module 203, configured to predict an interference coefficient for the sensor unit based on environmental parameters, so as to obtain the interference coefficient of environmental factors on the sensor;

[0086] A construction module 204, configured to perform virtual-real bidirectional mapping based on the interference coefficient and region information, and construct a driving test digital twin system corresponding to the test region, where the driving test digital twin system is used to map the physical system corresponding to the test region;

[0087] A driving test module 205, configured to control a test vehicle to perform a virtual driving test in the driving test digital twin system, so as to obtain a test result.

[0088] For a vehicle driving test device 200 in this embodiment provided by this application, first, a policy generation module 202 generates a sensor configuration policy for the test vehicle based on the region information of the test region obtained by an acquisition module 201, and configures the sensors of the test vehicle based on the sensor configuration policy, so that the configured sensors can match the test region for vehicle testing, reduce the participation of useless sensors in the test, and save the test cost. Then, a prediction module 203 predicts an interference coefficient for the sensor unit based on the environmental parameters of the test region, so as to obtain the interference coefficient of environmental factors on the sensor, and a construction module 204 performs virtual-real bidirectional mapping based on the interference coefficient and region information, and constructs a driving test digital twin system corresponding to the test region, where the driving test digital twin system maps the physical system corresponding to the test region, and a driving test module 205 controls the test vehicle to perform a virtual driving test in the driving test digital twin system, so as to obtain a test result. In this way, the invisible environmental parameters and visible region information of the test region can be added to the corresponding digital twin system, so as to improve the authenticity of the constructed driving test digital twin system, make the data collected by the sensors configured on the test vehicle during the virtual driving test highly match the real information of the test region, improve the accuracy of the test result obtained by the test, and thus improve the accuracy of vehicle testing.

[0089] Optionally, the prediction module 203 is specifically configured to:

[0090] Input the environmental parameters into a preset interference coefficient prediction model, so as to obtain the interference coefficient corresponding to the sensor output by the interference coefficient prediction model;

[0091] Wherein, the environmental parameters include temperature parameters, humidity parameters, and light intensity parameters;

[0092] The interference coefficient corresponding to the sensor includes a temperature interference coefficient, a humidity interference coefficient, and a light intensity interference coefficient.

[0093] Optionally, the prediction module 203 is specifically configured to:

[0094] Collect environmental monitoring data. The environmental observation data includes data obtained by monitoring environmental physical quantities under different environmental conditions. The environmental physical quantities include temperature, humidity, and light intensity;

[0095] Obtain the output signals of each sensor in the test area under different environmental conditions;

[0096] Input the output signals and environmental monitoring data into a preset initial model for training to obtain a model output;

[0097] Optimize and adjust the initial model based on the model output to obtain an interference coefficient prediction model.

[0098] Optionally, the driving test module 205 is specifically used for:

[0099] Determine the area type of the test area based on the area information;

[0100] Determine the corresponding test requirements based on the area information and the area type;

[0101] Determine the driving operation strategy of the test vehicle based on the test requirements;

[0102] Control the test vehicle to perform virtual driving tests in the driving test digital twin system according to the driving operation strategy to obtain test data;

[0103] Form test results based on the test data.

[0104] Optionally, the test area is configured with a data collection device; the acquisition module 201 is specifically used for:

[0105] Use the data collection device to collect the initial area information of the test area. The initial area information includes initial road information, initial traffic participant information, and initial traffic facility information;

[0106] Perform spatio-temporal synchronization processing and spatial alignment processing on the initial area information to obtain the area information of the test area.

[0107] Optionally, the policy generation module 202 is specifically used for:

[0108] Determine the area type of the test area based on the area information;

[0109] Search for the alternative sensor configuration policy corresponding to the area type from the preset configuration policy library, and use the alternative sensor configuration policy as the sensor configuration policy of the test vehicle.

[0110] It should be noted that a vehicle driving test device provided in the above embodiment and a vehicle driving test method provided in the above embodiment belong to the same concept. The specific manners in which each module and unit perform operations have been described in detail in the method embodiment, and will not be elaborated here. In practical applications, the vehicle driving test device provided in the above embodiment can, as needed, allocate the above functions to different functional modules, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above. This is not limited here either.

[0111] An intelligent cockpit system according to an embodiment of the present application applies the above vehicle driving test method. The intelligent cockpit system includes:

[0112] A data acquisition device for acquiring area information and environmental parameters of a test area;

[0113] A sensor unit configured on a test vehicle according to a sensor configuration strategy generated based on the area information;

[0114] An intelligent cockpit for performing virtual driving tests in a constructed driving test digital twin system instead of the test vehicle to obtain test results;

[0115] The data acquisition device, the sensor unit, and the intelligent cockpit are communicatively connected to each other.

[0116] In this embodiment provided by the present application, using communication protocols and data conversion technologies, the identity of the intelligent cockpit is mapped to a real vehicle in the real world. At the same time, the intelligent cockpit and the digital twin system are in the same local area network. The digital twin system automatically discovers and adds the intelligent cockpit as a new test vehicle, and through the internal registration mechanism and identity recognition of the system, generates a unique vehicle ID. In this way, the intelligent cockpit can be used to replace the real test vehicle to perform virtual driving tests in the constructed digital twin system, realizing the interconnection and interoperability of various data and control instructions in the intelligent cockpit with the simulated digital twin system, enabling the state and operations of the intelligent cockpit to be synchronized to the simulated digital twin system in real time, without the need to use real vehicles for testing, reducing the test cost. At the same time, the digital twin system can also automatically discover, add, and classify other devices in the same local area network, such as roadside computing units, roadside units, cameras, radars, etc. In this way, through the access and transformation of the intelligent cockpit and the reasonable addition of sensors, vehicle testing can more realistically simulate the autonomous driving state of actual vehicles, effectively verifying the performance and safety of the autonomous driving system in different scenarios.

[0117] A computing device according to an embodiment of the present application includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, it implements some or all of the steps of the above vehicle driving test method.

[0118] Among them, a computer can be selected as the computing device. Correspondingly, its program is computer software. For the various parameters and steps in a computing device of the present application above, reference can be made to the various parameters and steps in the embodiments of a vehicle driving test method in the foregoing text, which will not be elaborated here.

[0119] In an embodiment of the present application, there is a computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are running, the steps of the foregoing vehicle driving test method are executed.

[0120] Among them, the computer-readable storage medium can be a transient computer-readable storage medium or a non-transient computer-readable storage medium.

[0121] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes one or more instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method of the embodiment of the present disclosure. The foregoing computer-readable storage medium can be a non-transient computer-readable storage medium, including: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes, or can also be a transient computer-readable storage medium.

[0122] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Among them, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code. The foregoing module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0123] Those skilled in the art of the present application know that the present application can be implemented as a system, a method, or a computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be completely hardware, can also be completely software (including firmware, resident software, microcode, etc.), or can also be in the form of a combination of hardware and software, which is generally referred to as "device", "module", or "system" in this article. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable media contains computer-readable program code. The computer-readable storage medium can be, for example, but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above.

[0124] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0125] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A vehicle driving test method, characterized in that: include: Obtain regional information and environmental parameters of the test area; Generate a sensor configuration strategy for the test vehicle based on the area information, and perform sensor configuration on the test vehicle based on the sensor configuration strategy to obtain a sensor unit corresponding to the test vehicle, wherein the sensor unit includes one or more sensors; Predicting the interference coefficient of the sensor unit based on the environmental parameters to obtain the interference coefficient of the environmental factors on the sensor; Based on the interference coefficient and the area information, a virtual-real bidirectional mapping is performed to construct a driving test digital twin system corresponding to the test area, and the driving test digital twin system is used to map the physical system corresponding to the test area; The test vehicle is controlled to perform a virtual driving test in the driving test digital twin system to obtain a test result.

2. The method according to claim 1, characterized in that The predicting the interference coefficient of the sensor unit based on the environmental parameter to obtain the interference coefficient of the environmental factor on the sensor includes: Inputting the environmental parameters into a preset interference coefficient prediction model to obtain an interference coefficient corresponding to the sensor output by the interference coefficient prediction model; Wherein, the environmental parameters include temperature parameters, humidity parameters and light intensity parameters; The interference coefficients corresponding to the sensor include the temperature interference coefficient, the humidity interference coefficient and the light intensity interference coefficient.

3. The method according to claim 2, characterized in that The construction method of the interference coefficient prediction model includes: Collecting environmental monitoring data, the environmental observation data includes data obtained by monitoring environmental physical quantities under different environmental conditions, the environmental physical quantities include temperature, humidity and light intensity; Obtaining output signals of each sensor in the test area when it is under different environmental conditions; Inputting the output signal and the environmental monitoring data into a preset initial model for training to obtain a model output; The initial model is optimized and adjusted based on the model output to obtain an interference coefficient prediction model.

4. The method according to claim 1, characterized in that The controlling the test vehicle to perform a virtual driving test in the driving test digital twin system to obtain a test result includes: determining an area type of the test area based on the area information; Determine corresponding test requirements based on the area information and the area type; Determining a driving operation strategy of the test vehicle based on the test requirements; Controlling the test vehicle to perform a virtual driving test in the driving test digital twin system according to the driving operation strategy to obtain test data; A test result is generated based on the test data.

5. The method according to claim 1, characterized in that The test area is provided with a data acquisition device; the obtaining of the area information of the test area includes: Using a data acquisition device to collect initial area information of a test area, the initial area information includes initial road information, initial traffic participant information, and initial traffic facility information; The initial area information is subjected to time-space synchronization processing and space alignment processing to obtain area information of the test area.

6. The method according to claim 1, characterized in that The generating of the sensor configuration strategy of the test vehicle based on the area information includes: determining an area type of the test area based on the area information; An alternative sensor configuration strategy corresponding to the area type is searched from a preset configuration strategy library, and the alternative sensor configuration strategy is used as the sensor configuration strategy of the test vehicle.

7. A vehicle driving test device, characterized in that: include: An acquisition module is used to obtain the area information and environmental parameters of the test area; A strategy generation module, used to generate a sensor configuration strategy for a test vehicle based on the area information, and perform sensor configuration on the test vehicle based on the sensor configuration strategy to obtain a sensor unit corresponding to the test vehicle, wherein the sensor unit includes one or more sensors; A prediction module, used to predict the interference coefficient of the sensor unit based on the environmental parameters to obtain the interference coefficient of the environmental factors on the sensor; A construction module, used to perform virtual-real bidirectional mapping based on the interference coefficient and the area information, and to construct a driving test digital twin system corresponding to the test area, wherein the driving test digital twin system is used to map the physical system corresponding to the test area; The driving test module is used to control the test vehicle to perform a virtual driving test in the driving test digital twin system to obtain a test result.

8. An intelligent cockpit system, characterized in that: Applying a vehicle driving test method as claimed in any one of claims 1 to 6, the smart cockpit system comprises: A data acquisition device, used to collect regional information and environmental parameters of the test area; A sensor unit configured on a test vehicle based on a sensor configuration strategy generated based on the area information; A smart cockpit, used to replace the test vehicle to perform a virtual driving test in the constructed driving test digital twin system to obtain a test result; The data acquisition device, the sensor unit and the smart cockpit are communicatively connected with each other.

9. A computing device comprising a memory, a processor, and a program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of a vehicle driving test method as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device executes the steps of a vehicle driving test method as described in any one of claims 1 to 6.

Images